© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 63497
    Prev
    Next
    INDEX
    Explanations

    history of knowledge power

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    幸
    -0.10
    èģļä¼ļ
    -0.09
    ä¸įæĺĵ
    -0.09
    奢åįİ
    -0.09
    羣æŃ£åģļåĪ°
    -0.09
    称ä¹ĭ
    -0.09
     ÙĪعدÙħ
    -0.08
     ÑģлÑĥж
    -0.08
    è´µ
    -0.08
    éĢĤ度
    -0.08
    POSITIVE LOGITS
    è´·
    0.09
    ORIZ
    0.09
    caler
    0.08
    olon
    0.08
    让æĪij
    0.08
    åĨħéĻĨ
    0.08
    alen
    0.08
    antal
    0.08
    ALK
    0.08
    æĺİæĹ¥
    0.08
    Activations Density 0.077%

    No Known Activations